Upload
amela-harrell
View
14
Download
0
Embed Size (px)
DESCRIPTION
An Overview of Core CI Technologies. Lyndon While. Evolutionary Algorithms (EAs). Reading: X. Yao, “Evolutionary computation: a gentle introduction”, Evolutionary Optimization, 2002 - PowerPoint PPT Presentation
Citation preview
CITS7212: Computational IntelligenceAn Overview of Core CI Technologies
An Overview of Core CI Technologies
Lyndon While
CITS7212: Computational IntelligenceAn Overview of Core CI Technologies
Evolutionary Algorithms (EAs)
Reading:
X. Yao, “Evolutionary computation: a gentle introduction”, Evolutionary Optimization, 2002
T. Bäck, U. Hammel, and H.-P. Schwefel, “Evolutionary computation: comments on the history and current state”, IEEE Transactions on Evolutionary Computation 1(1), 1997
CITS7212: Computational Intelligence
The Nature-Inspired Metaphor
Inspired by Darwinian natural selection:– population of individuals exists in some environment– competition for limited resources creates selection
pressure: the fitter individuals that are better adapted to the environment are rewarded more than the less fit
– fitter individuals act as parents for the next generation– offspring inherit properties of their parents via genetic
inheritance, typically sexually through crossover with some (small) differences (mutation)
– over time, natural selection drives an increase in fitness
EAs are population-based “generate-and-test” stochastic search algorithms
An Overview of Core CI Technologies 3
CITS7212: Computational Intelligence
Terminology
Gene: the basic heredity unit in the representation of individuals
Genotype: the entire genetic makeup of an individual – the set of genes it possess
Phenotype: the physical manifestation of the genotype in the environment
Fitness: evaluation of the phenotype at solving the problem of interest
Evolution occurs in genotype space based on fitness performance in phenotype space
An Overview of Core CI Technologies 4
5
CITS7212: Computational Intelligence
The Evolutionary Cycle
An Overview of Core CI Technologies 5
Termination
Initialisation
Population
Parents
Offspring
Parent selection
Survivor selection
Genetic variation(mutation and recombination)
CITS7212: Computational Intelligence
245 6 8 5
XX
An Example
An Overview of Core CI Technologies 6
CITS7212: Computational Intelligence
EA Variants
There are many different EA variants/flavours:– differences are mainly cosmetic and often irrelevant – the similarities dominate the differences
Variations differ predominately on representation:– genetic algorithms (GAs): binary strings– evolution strategies (ESs): real-valued vectors– genetic programming (GP): expression trees– evolutionary programming (EP): finite state machines
and also on their historical origins/aims, and their emphasis on different variation operators and selection schemes
An Overview of Core CI Technologies 7
CITS7212: Computational Intelligence
Designing an EA
Best approach for designing an EA:– choose a representation to suit the problem, ensuring
(all) interesting solutions can be represented– create a fitness function with a useful search gradient– choose variation operators to suit the representation,
being mindful of any search bias – choose selection operators to ensure efficiency while
avoiding premature convergence to local optima– tune parameters and operators to the specific problem
Need to balance exploration and exploitation:– variation operations create diversity and novelty– selection rewards quality and decreases diversity
An Overview of Core CI Technologies 8
CITS7212: Computational IntelligenceAn Overview of Core CI Technologies
Neural Networks (NNs)
Reading:
S. Russell and P. Norvig, Section 20.5, Artificial Intelligence: A Modern Approach, Prentice Hall, 2002
G. McNeil and D. Anderson, “Artificial Neural Networks Technology”, The Data & Analysis Center for Software Technical Report, 1992
CITS7212: Computational Intelligence
The Nature-Inspired Metaphor
Inspired by the brain:– neurons are structurally
simple cells that aggregate and disseminate electrical signals
– computational power and intelligence emerges from the vast interconnected network of neurons
NNs act as function approximators or pattern recognisers which learn from observed data
An Overview of Core CI Technologies 10
Diagrams taken from a report on neural networks by C. Stergiou and D. Siganos
CITS7212: Computational Intelligence
The Neuron Model
A neuron combines values via its input and activation functions
The bias determines the threshold needed for a “positive” response
Single-layer neural networks (perceptrons) can represent only linearly-separable functions
An Overview of Core CI Technologies 11
n
j
jiji aWga0
,
g
ia
iW ,0
ijW ,ja
10 a
InputLinks
Output Links
Output
Bias Weight
ActivationFunction
InputFunction
CITS7212: Computational Intelligence
Multi-Layered Neural Networks
A network is formed by the connections (links) of many nodes – inputs to outputs through one or more hidden layers
Link weights control the behaviour of the function represented by the NN– adjusting the weights
changes the encoded function
An Overview of Core CI Technologies 12
CITS7212: Computational Intelligence
Multi-Layered Neural Networks
Hidden layers increase the “power” of the NN at the cost of extra complexity and training time:– perceptrons capture only linearly-separable functions– an NN with a single (sufficiently large) hidden layer can
represent any continuous function with arbitrary accuracy– two hidden layers are needed to represent
discontinuous functions
There are two main types of multi-layered NNs:1. feed-forward: simple acyclic structure – the stateless
encoding allows functions of just its current input
2. recurrent: cyclic feedback loops are allowed – the stateful encoding supports short-term memory
An Overview of Core CI Technologies 13
CITS7212: Computational Intelligence
Training Neural Networks
Training means adjusting link weights to minimise some measure of error (the cost function)– i.e. learning is an optimisation search in weight space
Any search algorithm can be used, most commonly gradient descent (back propagation)
Common learning paradigms:1. supervised learning: training is by comparison with
known input/output examples (a training set)
2. unsupervised learning: no a priori training set is provided; the system discovers patterns in the input
3. reinforcement learning: training uses environmental feedback to assess the quality of actions
An Overview of Core CI Technologies 14
CITS7212: Computational IntelligenceAn Overview of Core CI Technologies
Questions?